CrabOS: An Operating System for Human-AI Co-inhabitation
Artificial IntelligenceHuman-Computer InteractionOperating Systems
Summary
The authors explain that AI agents and humans often need to take turns working on the same task, but current systems keep their work separate, making it hard to share progress smoothly. They introduce Human-AI Co-inhabitation, a new type of work environment where humans and AI can work together seamlessly by sharing the same readable work state. To make this idea practical, the authors created CrabOS, a system that lets both humans and AI access and change the task information directly without extra tools. Their studies show that CrabOS makes it easier to handle complex tasks that switch between human and AI control.
Authors
Qi Yang, Yun Ma
Abstract
AI agents are evolving into long-running computational entities that can invoke tools, maintain memory, and complete complex tasks across applications. In real-world settings, completing a task often requires humans and AI to take turns leading its execution. Such alternation depends on the seamless handoff of the work state of the task between humans and AI. Existing agent systems, however, provide humans and AI with separate work environments. AI agents must therefore rely on additional bridges to continue work: either developers build task-specific interfaces to access the work state, or users manually transfer relevant parts of it through screenshots or textual descriptions. Both approaches make handoffs costly and scale poorly. We propose Human-AI Co-inhabitation, a type of work environment that enables humans and AI to seamlessly take turns continuing work on the same task, and design and implement CrabOS to realize this concept. CrabOS represents the work state as natural-language-readable text objects shared by humans and AI, allowing both to access and manipulate it directly through the same auditable interface without bridges. Case studies show that CrabOS elevates support for complex tasks with alternating human and AI leadership from bridge-dependent application-level solutions to native operating-system capabilities, which provide a new foundation for developing and running AI agents.